AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Conditional Latent Diffusion Models for Zero-Shot Instance Segmentation

Maximilian Ulmer, Wout Boerdijk, Rudolph Triebel, Maximilian Durner

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Prompted SAM segmentation · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the refine model after the coarse model (ablation)OC-DiT · BOP TUDLAP: 32.5 -> 59.4Improved
add the refine model after the coarse model (ablation)OC-DiT · BOP LMOAP: 29.6 -> 40.1Improved
add the refine model after the coarse model (ablation)OC-DiT · BOP YCBVAP: 68.6 -> 71.7Improved
train with random-interval positional encodings on 8 objects and test on 16, instead of training on 16 objects directly (ablation)OC-DiT · YCBVAP: 60.3 -> 65.2Improved
interpolate positional encodings at test time instead of random interval training (ablation)OC-DiT · YCBVAP: 65.2 -> 55.6Hurt
add Objaverse-based synthetic training data to MegaPose GSO (ablation)OC-DiT · YCBVAP: 56.3 -> 63.1Improved
train on all three datasets rather than any subset (ablation)OC-DiT · YCBVAP: 62.0 -> 65.5Improved
add GSO segmentation data to Objaverse data (ablation)OC-DiT · YCBVAP: 62.0 -> 62.0No clear effect
increase number of diffusion steps beyond 9 (ablation)OC-DiT · YCBVAPNo clear effect
vary noise discretization rho (ablation)OC-DiT · YCBVAPNo clear effect
increase test-time ensemble size with spatial augmentations (ablation)OC-DiT · YCBVAPImproved
condition refine model on all objects (without true label) instead of the true object (ablation)OC-DiT refine · TUDLAP: 65.4 -> 56.8Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy